© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9591
    Prev
    Next
    INDEX
    Explanations

    names of authors and contributors in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newspaper
    -0.43
    姨
    -0.41
     episcopal
    -0.40
     instant
    -0.38
     Hurd
    -0.38
     sá
    -0.38
     مخطط
    -0.38
    出品
    -0.38
     yii
    -0.38
    Alleg
    -0.38
    POSITIVE LOGITS
     snippetHide
    0.61
     Roskov
    0.59
    Datuak
    0.59
     ModelExpression
    0.55
    webElementXpaths
    0.55
     ddelweddau
    0.54
    LookAnd
    0.54
     ब्रेकडाउन
    0.54
    ⓧ
    0.53
     '\\;'
    0.52
    Activations Density 0.097%

    No Known Activations